Demystifying the Recency Heuristic in Temporal-Difference Learning.
Brett DaleyMarlos C. MachadoMartha WhitePublished in: CoRR (2024)
Keyphrases
- temporal difference learning
- fixed point
- function approximation
- reinforcement learning
- evaluation function
- game playing
- approximate value iteration
- temporal difference
- optimal solution
- markov decision process
- evolutionary algorithm
- dynamic programming
- function approximators
- search algorithm
- policy iteration
- reinforcement learning algorithms
- model selection
- real valued
- neural network
- sufficient conditions
- linear programming
- state space
- pairwise
- training data
- machine learning